Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp8k661zp
Results Ready
Name
parakeet_tdt_decoder
Target Device
  • Samsung Galaxy S26
  • Android 16
  • Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
token_id: int32[1, 1]
h_in: float32[2, 1, 640]
c_in: float32[2, 1, 640]
Completion Time
11/15/2026, 1:31:18 PM
Options
--qairt_version latest
Versions
  • ONNX Runtime: 1.30.0
  • QNN Execution Provider: 2.5.0
  • QAIRT: v2.51.0.260929181845
  • Android: 16 (BP4A.251205.006)
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
160 μs
Estimated Peak Memory Usage
0 ‑ 33 MB
Compute Units
NPU
59
CPU
3
StageTimeMemory
First App Load
694 ms103‑111 MB
Subsequent App Load
232 ms1‑36 MB
Inference
160 μs0‑33 MB
ONNX RuntimeValue
execution_modeSEQUENTIAL
intra_op_num_threads0
inter_op_num_threads0
enable_memory_patternfalse
enable_cpu_memory_arenafalse
graph_optimization_levelENABLE_ALL
QNN Execution ProviderValue
htp_performance_mode"burst"
htp_graph_finalization_optimization_mode"3"
enable_htp_fp16_precision"1"
capture_network_visualizationsfalse
context_priority"normal"
offload_graph_io_quantization"1"
num_graph_prepare_threads"1"

Sign up to run this model on a hosted Qualcomm® device!

Run on device